© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49980
    Prev
    Next
    INDEX
    Explanations

    varying states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     जिम्मे
    0.44
     mathcolor
    0.39
    examtype
    0.38
    saf
    0.38
    hafte
    0.38
    示
    0.38
    छाड़
    0.37
    ]^
    0.37
     아멘
    0.37
    isors
    0.36
    POSITIVE LOGITS
     varying
    0.69
    varying
    0.61
     smoothed
    0.49
     boarded
    0.48
     ordered
    0.47
     mapped
    0.47
     mated
    0.46
     fluctuating
    0.46
     established
    0.45
     Vary
    0.45
    Activations Density 0.007%

    No Known Activations